Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    subtle contrasts and elements of moderation or slight changes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vast
    -0.55
     ríos
    -0.52
     entire
    -0.51
     justru
    -0.46
     una
    -0.46
    くちゃ
    -0.46
     تمام
    -0.45
     full
    -0.45
    Vast
    -0.44
     exact
    -0.43
    POSITIVE LOGITS
     المعيارى
    1.02
     Quelques
    1.00
     briefly
    0.99
     trochę
    0.97
     Etwas
    0.96
     qualche
    0.92
     nieco
    0.92
    存于互联网档案馆
    0.92
     Alguns
    0.91
    Somewhat
    0.91
    Act Density 0.810%

    No Known Activations